04-market-sizing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web search results and external Notion pages to generate market reports, creating a surface for indirect prompt injection.
- Ingestion points: Reads target market and account tier data from a Notion page and fetches market data via
WebSearch(SKILL.md). - Boundary markers: No explicit instructions are provided to the AI to distinguish between the skill's instructions and potentially malicious instructions embedded in the external data.
- Capability inventory: The skill uses
WebSearchto retrieve arbitrary web content and has the permission to create or update Notion pages (SKILL.md). - Sanitization: There are no explicit sanitization, validation, or filtering mechanisms described to handle potentially malicious input from the web search results.
Audit Metadata